Limited-memory BFGS
PulseAugur coverage of Limited-memory BFGS — every cluster mentioning Limited-memory BFGS across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New empirical Bayes approach enhances generalized linear models
Researchers have developed a novel empirical Bayes approach for fitting Bayesian generalized linear models, introducing a mean-field variational inference method that estimates the prior within the algorithm, making it …
-
New research tackles PINN limitations with error correction, precision, and shallow architectures
Three recent research papers explore methods to improve the performance and efficiency of Physics-Informed Neural Networks (PINNs). One approach, Physics-Informed Error Field Learning (PIEFL), introduces an auxiliary er…
-
New blockwise optimizer enhances cubic Newton methods for large-scale neural networks
This paper introduces a novel blockwise optimizer designed to improve the efficiency of cubic regularized Newton methods for large-scale neural network training. The proposed method handles arbitrarily large parameter t…
-
Levi-Civita Coordinates Improve Dynamics, Worsen Optimization in AI Dynamics Study
Researchers have explored the use of Levi--Civita coordinates for learned Hamiltonian dynamics, comparing them to Cartesian formulations in a perturbed Kepler system. While Levi--Civita coordinates demonstrated superior…
-
New Two-Sided L-BFGS algorithm enhances optimization stability
Researchers have developed a new variant of the limited-memory BFGS (L-BFGS) optimization algorithm, called Two-Sided L-BFGS. This method addresses the issue of exploding condition numbers in the inverse Hessian approxi…
-
Hybrid deep learning method improves laser wavefront reconstruction
Researchers have developed a novel hybrid method for reconstructing wavefront distortions in laser systems, aiming to improve efficiency and accuracy. This approach combines a convolutional neural network for initial es…
-
New research explores genetic programming for symbolic regression · 2 sources tracked
Two recent arXiv papers explore genetic programming (GP) for symbolic regression (SR). One study, "Evaluation of Population Initialization Methods for Genetic Programming-based Symbolic Regression," found that different…
-
DualTCN framework uses AI to improve marine CSEM data inversion accuracy
Researchers have developed DualTCN, a novel deep learning framework for analyzing time-domain marine controlled-source electromagnetic (MCSEM) data. This framework moves beyond traditional methods by directly reconstruc…
-
Random test functions, $H^{-1}$ norm equivalence, and stochastic variational physics-informed neural networks
Researchers have developed a new method for solving partial differential equations using stochastic variational physics-informed neural networks (SV-PINNs). This approach leverages the equivalence between the $H^{-1}$ n…